Skills › Reinforcement Learning

RL Foundations

Understand MDPs, the Bellman equation, and basic Q-learning.

0%
Confidence · no data yet
Sign in to track

After this skill you can…

  • Formalise a problem as an MDP
  • Implement tabular Q-learning on CartPole
  • Explain exploration vs exploitation tradeoff

Watch (10 videos)

Build a Doom AI Model with Python | Gaming Reinforcement Learning Full Course
Nicholas Renotte · beginner hands-on
→ Build a Reinforcement Learning model→ Train an AI agent to play Doom
Deep Reinforcement Learning for Atari Games Python Tutorial | AI Plays Space Invaders
Nicholas Renotte · beginner hands-on
→ Build AI models for game playing→ Train models with Reinforcement Learning
Training & Testing Deep reinforcement learning (DQN) Agent - Reinforcement Learning p.6
sentdex · beginner hands-on
→ Train a DQN agent→ Test a DQN agent→ Implement Q-learning in Python
How to Win Slot Machines - Intro to Deep Learning #13
Siraj Raval · beginner hands-on
→ Solve the multi-armed bandit problem→ Implement policy gradients
Proximal Policy Optimization Implementation: 9 Atari-specific Details (2/3)
Weights & Biases · beginner hands-on
→ Implement PPO for Atari games→ Apply PPO to robotics control
Landing a SpaceX Falcon Heavy Rocket
Siraj Raval · beginner hands-on
→ Train a reinforcement learning agent using TensorFlow and Gym→ Simulate rocket landing using machine learning
Real Life Reinforcement Learning: Building and Training a CartPole
Weights & Biases · beginner hands-on
→ Design a CartPole robot→ Train a reinforcement learning model
Reinforcement Learning Live Example With My Baby 👶👶👶
Krish Naik · beginner hands-on
→ Implement Reinforcement Learning algorithms→ Apply RL to real-world problems
Reinforcement Learning in 3 Hours | Full Course using Python
Nicholas Renotte · beginner hands-on
→ Build deep learning powered agents→ Solve RL problems using OpenAI Gym and Stable Baselines
A Guide to DeepMind's StarCraft AI Environment
Siraj Raval · beginner hands-on
→ Install StarCraft AI Environment→ Run a pre-trained Deep Q model